A Multi-sensor Fusion Based Acc Target Vehicle Recognition Method for Curves

Abstract

The invention discloses a method for identifying a curved ACC target vehicle based on multi-sensor fusion, which belongs to the field of assisted driving. Install the vehicle-mounted camera and millimeter-wave radar on the vehicle according to certain requirements, use the CAN bus to obtain its output information, and eliminate the empty targets, invalid targets and opposing vehicle targets output by the radar to obtain effective tracking targets. The vehicle camera and the millimeter-wave radar are spatially synchronized so that the data of the two sensors are in the same coordinate system, and then time-synchronized to solve the problem that the sampling time points of the two sensors are not synchronized. According to the data of the on-board camera, the curve driving area is established, the target data output by the radar is matched with it, the vehicle in the current lane is determined, and finally the final tracking target of the main vehicle is determined according to the principle of the shortest distance. The invention utilizes the fusion technology of the vehicle-mounted camera and the millimeter-wave radar, and realizes the effective recognition of the target tracking vehicle in the curve by establishing the curve driving area and matching the radar data.

Description

technical field [0001] The invention relates to an effective target recognition method for ACC vehicles under a curve driving condition, in particular to a method for recognizing a curve ACC target vehicle based on multi-sensor fusion. Background technique [0002] Target recognition and tracking in curves is an important topic in the field of environmental perception, and has an important impact on the development of ADAS (Advanced Driving Assistant System) systems. Taking the ACC (Adaptive Cruise Control) system as an example, the existing method mainly adjusts the speed of the cruise vehicle adaptively based on the millimeter-wave radar information, and maintains a safe distance from the vehicle in front of the lane. However, on a curved road section, there are usually multiple target vehicles in front of the cruiser or the target vehicle exceeds the preset lane range. Accidents caused by abnormal acceleration or deceleration. In addition, considering the characteristic...

AI Technical Summary

Problems solved by technology

However, on a curved road section, there are usually multiple target vehicles in front of the cruiser or the target vehicle exceeds the preset lane range. Accidents caused by abnormal acceleration or deceleration

In addition, considering the characteristics of the radar itself, information on metal objects such as guardrails, buildings, and signboards on both sides of the curve will also be transmitted back by the radar. These objects may generate false alarms for vehicle control and cause traffic accidents. , affecting the normal operation of the expressway

[0003] Most of the existing methods use machine vision recognition technology or millimeter-wave radar data flags (moving, new targets, etc.) to identify the targets in front of the vehicle. For objects on the straight road, there is a high recognition rate, but in the bend At the road, the accuracy rate will be greatly reduced

Images